. Author manuscript; available in PMC: 2021 Mar 18.

Published in final edited form as: IEEE/ACM Trans Audio Speech Lang Process. 2019 Aug 12;27(11):1839–1848. doi: 10.1109/taslp.2019.2934319

TABLE V.

Separation results and comparisons for a pair of male-male speakers. Results are shown at TIR = −6 dB, averaged over all T₆₀ conditions.

Metric	ESTOI	PESQ	ΔSDR
Unprocessed	23.9	1.21	0.00
Talker-independent	36.4	1.56	3.19
Target-dependent	39.2	1.77	3.41
One-stage talker-dependent	49.5	2.00	5.26
Two-stage talker-dependent	50.1*	2.02	5.40*